ENHANCING NETWORK INTRUSION DETECTION USING MACHINE LEARNING AND META-MODELLING FOR IMPROVED CYBER SECURITY PERFORMANCE

This study is based on the analysis of network intrusion detection and the improvement of various machine learning methods that produce high accuracy and guarantee secure network traffic from malicious activities. The work employs Gradient Boosting, Random Forest, and Neural Network classifiers alongside a meta-model that improves the performance of learning models among them. Data enhancements that were used in the models include data normalization and feature selection in a bid to enhance the accuracy of the model’s predictions. Common parameters such as accuracy, precision, recall, and F1-score were computed on each model to allow for a comparative evaluation. Therefore, the meta-model reveals better results than individual base models, meaning the meta-model can be efficient for real-time intrusion detection. This research aids in enhancing the accuracy and reliability of the IDS model for subsequent improvements in cybersecurity applications.